Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    following "this"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     typename
    1.02
     ())
    0.95
     ();
    0.84
     Musée
    0.84
    eulerAngles
    0.83
     extremal
    0.83
    。,
    0.82
     extrémités
    0.81
     extremes
    0.81
     typer
    0.79
    POSITIVE LOGITS
     অতঃপর
    0.86
     عبر
    0.83
     shuffling
    0.78
    क्स
    0.77
     जस्टिस
    0.74
    alassem
    0.74
     অবশেষে
    0.74
    Ahead
    0.73
     विपक्षी
    0.73
     personnel
    0.73
    Act Density 0.000%

    No Known Activations